INDEX

Explanations

references to data tables and their descriptions within the text

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Orrell

-0.65

сылкі

-0.57

ⓧ

-0.57

 оригіналу

-0.56

HomeAsUpEnabled

-0.55

igshid

-0.55

ingar

-0.53

 ddelweddau

-0.52

ýt

-0.50

Réalisation

-0.50

POSITIVE LOGITS

 Table

1.54

 table

1.54

 tables

1.39

 Tables

1.35

Table

1.34

 tabel

1.17

Tables

1.12

TABLE

1.10

 TABLE

1.09

table

1.08

Activations Density 0.149%

references to data tables and their descriptions within the text

No Comments

No Known Activations